linux/fs/pidfs.c

// SPDX-License-Identifier: GPL-2.0
#include <linux/anon_inodes.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/magic.h>
#include <linux/mount.h>
#include <linux/pid.h>
#include <linux/pidfs.h>
#include <linux/pid_namespace.h>
#include <linux/poll.h>
#include <linux/proc_fs.h>
#include <linux/proc_ns.h>
#include <linux/pseudo_fs.h>
#include <linux/ptrace.h>
#include <linux/seq_file.h>
#include <uapi/linux/pidfd.h>
#include <linux/ipc_namespace.h>
#include <linux/time_namespace.h>
#include <linux/utsname.h>
#include <net/net_namespace.h>

#include "internal.h"
#include "mount.h"

#ifdef CONFIG_PROC_FS
/**
 * pidfd_show_fdinfo - print information about a pidfd
 * @m: proc fdinfo file
 * @f: file referencing a pidfd
 *
 * Pid:
 * This function will print the pid that a given pidfd refers to in the
 * pid namespace of the procfs instance.
 * If the pid namespace of the process is not a descendant of the pid
 * namespace of the procfs instance 0 will be shown as its pid. This is
 * similar to calling getppid() on a process whose parent is outside of
 * its pid namespace.
 *
 * NSpid:
 * If pid namespaces are supported then this function will also print
 * the pid of a given pidfd refers to for all descendant pid namespaces
 * starting from the current pid namespace of the instance, i.e. the
 * Pid field and the first entry in the NSpid field will be identical.
 * If the pid namespace of the process is not a descendant of the pid
 * namespace of the procfs instance 0 will be shown as its first NSpid
 * entry and no others will be shown.
 * Note that this differs from the Pid and NSpid fields in
 * /proc/<pid>/status where Pid and NSpid are always shown relative to
 * the  pid namespace of the procfs instance. The difference becomes
 * obvious when sending around a pidfd between pid namespaces from a
 * different branch of the tree, i.e. where no ancestral relation is
 * present between the pid namespaces:
 * - create two new pid namespaces ns1 and ns2 in the initial pid
 *   namespace (also take care to create new mount namespaces in the
 *   new pid namespace and mount procfs)
 * - create a process with a pidfd in ns1
 * - send pidfd from ns1 to ns2
 * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid
 *   have exactly one entry, which is 0
 */
static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
{ … }
#endif

/*
 * Poll support for process exit notification.
 */
static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
{ … }

static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{ … }

static const struct file_operations pidfs_file_operations = …;

struct pid *pidfd_pid(const struct file *file)
{ … }

static struct vfsmount *pidfs_mnt __ro_after_init;

#if BITS_PER_LONG == 32
/*
 * Provide a fallback mechanism for 32-bit systems so processes remain
 * reliably comparable by inode number even on those systems.
 */
static DEFINE_IDA(pidfd_inum_ida);

static int pidfs_inum(struct pid *pid, unsigned long *ino)
{
	int ret;

	ret = ida_alloc_range(&pidfd_inum_ida, RESERVED_PIDS + 1,
			      UINT_MAX, GFP_ATOMIC);
	if (ret < 0)
		return -ENOSPC;

	*ino = ret;
	return 0;
}

static inline void pidfs_free_inum(unsigned long ino)
{
	if (ino > 0)
		ida_free(&pidfd_inum_ida, ino);
}
#else
static inline int pidfs_inum(struct pid *pid, unsigned long *ino)
{ … }
#define pidfs_free_inum(ino) …
#endif

/*
 * The vfs falls back to simple_setattr() if i_op->setattr() isn't
 * implemented. Let's reject it completely until we have a clean
 * permission concept for pidfds.
 */
static int pidfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
			 struct iattr *attr)
{ … }


/*
 * User space expects pidfs inodes to have no file type in st_mode.
 *
 * In particular, 'lsof' has this legacy logic:
 *
 *	type = s->st_mode & S_IFMT;
 *	switch (type) {
 *	  ...
 *	case 0:
 *		if (!strcmp(p, "anon_inode"))
 *			Lf->ntype = Ntype = N_ANON_INODE;
 *
 * to detect our old anon_inode logic.
 *
 * Rather than mess with our internal sane inode data, just fix it
 * up here in getattr() by masking off the format bits.
 */
static int pidfs_getattr(struct mnt_idmap *idmap, const struct path *path,
			 struct kstat *stat, u32 request_mask,
			 unsigned int query_flags)
{ … }

static const struct inode_operations pidfs_inode_operations = …;

static void pidfs_evict_inode(struct inode *inode)
{ … }

static const struct super_operations pidfs_sops = …;

/*
 * 'lsof' has knowledge of out historical anon_inode use, and expects
 * the pidfs dentry name to start with 'anon_inode'.
 */
static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen)
{ … }

static const struct dentry_operations pidfs_dentry_operations = …;

static int pidfs_init_inode(struct inode *inode, void *data)
{ … }

static void pidfs_put_data(void *data)
{ … }

static const struct stashed_operations pidfs_stashed_ops = …;

static int pidfs_init_fs_context(struct fs_context *fc)
{ … }

static struct file_system_type pidfs_type = …;

struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags)
{ … }

void __init pidfs_init(void)
{ … }